Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13529
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "prep" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "prep" and its variations, indicating a focus on preparation-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scape
    -0.73
     independents
    -0.68
    âĸ¬
    -0.67
     charism
    -0.64
     Butterfly
    -0.61
    âĸ¬âĸ¬
    -0.61
     Iranians
    -0.60
     Rampage
    -0.60
     Albion
    -0.59
    ktop
    -0.59
    POSITIVE LOGITS
    oster
    1.47
    onder
    1.45
    ubes
    1.34
    ublic
    1.22
    otent
    1.17
    regnancy
    1.07
    ulse
    1.00
    aired
    0.97
    ounding
    0.95
    uce
    0.94
    Activations Density 0.021%

    No Known Activations